duyphu commited on
Commit
5f36e66
·
verified ·
1 Parent(s): 3695b0c

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14485db505cc8c0686e85a4c73b2790b842ebb0c8fdef015be903020e5908369
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fa4af5ea6ebabbe2ac1e745ee529fe3305d4e24e4a2f705efa8b89b9cf66a6
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bebc706a86a2eae0bacf912d7adcf8bf902852e6b05d8e2f50268bee22594843
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79fd6034a7e8fad5ee374fc6097cb2ca1ce43c59e22a22ef62098b1ba27916c4
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.004568617114742576,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.9891,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9617734090358784.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006852925672113864,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.9891,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.005271481286241434,
72
+ "grad_norm": 0.6719041466712952,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.8862,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.005271481286241434,
79
+ "eval_loss": 0.9079647660255432,
80
+ "eval_runtime": 297.29,
81
+ "eval_samples_per_second": 8.063,
82
+ "eval_steps_per_second": 4.033,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.006150061500615006,
87
+ "grad_norm": 0.5712262392044067,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.8628,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.4426601135538176e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null